Kazuya Matsumoto, Naohito Nakasato, Stanislav G. Sedukhin. Implementing a Code Generator for Fast Matrix Multiplication in OpenCL on the GPU. In IEEE 6th International Symposium on Embedded Multicore/Manycore SoCs, MCSoC 2012, Fukushima, Japan, September 20-22, 2012. pages 198-204, IEEE Computer Society, 2012. [doi]
@inproceedings{MatsumotoNS12-1, title = {Implementing a Code Generator for Fast Matrix Multiplication in OpenCL on the GPU}, author = {Kazuya Matsumoto and Naohito Nakasato and Stanislav G. Sedukhin}, year = {2012}, doi = {10.1109/MCSoC.2012.30}, url = {https://doi.org/10.1109/MCSoC.2012.30}, researchr = {https://researchr.org/publication/MatsumotoNS12-1}, cites = {0}, citedby = {0}, pages = {198-204}, booktitle = {IEEE 6th International Symposium on Embedded Multicore/Manycore SoCs, MCSoC 2012, Fukushima, Japan, September 20-22, 2012}, publisher = {IEEE Computer Society}, isbn = {978-1-4673-2535-6}, }